基于路面分割的高精度地图创建优化方法研究
|
摘要
高精度地图主要利用已采集图像的地面信息生成,但是在真实环境中图像的地面信息容易受动态障碍物遮挡,同时GPS难免会有抖动误差,导致地图拼接效果并不理想。针对上述问题提出了一种基于路面分割的动态障碍物去除与图像配准方法。使用深度学习对全景图像进行语义分割并提取路面信息,在去除动态障碍物干扰后,利用路面特征进行图像配准。融合GPS与里程计信息进行定位优化,利用多帧图像叠加填补空缺形成地图。最终,实验验证了该方法在去除动态障碍物的同时也提高了地图的精度。
High-precision maps are mainly generated by using ground information of acquired images. But in the real environment, the ground information of image is easily occluded by dynamic obstacles, and GPS will inevitably have jitter errors, resulting in the map mosaic problems. Therefore, this paper proposes a dynamic obstacle removal method and an image registration method based on the road segmentation for the aforementioned problems. In-depth learning is used to semantically segment panoramic images and extract pavement information. Pavement features are used for image registration and removal of dynamic obstacle occlusion can also improve the accuracy of registration. GPS and odometer information are fused for positioning optimization, and multi-frame image overlay is used to fill the gaps to form a map. Finally, the experimental results show that this method improves the accuracy of map while removing dynamic obstacles.
High-precision maps are mainly generated by using ground information of acquired images. But in the real environment, the ground information of image is easily occluded by dynamic obstacles, and GPS will inevitably have jitter errors, resulting in the map mosaic problems. Therefore, this paper proposes a dynamic obstacle removal method and an image registration method based on the road segmentation for the aforementioned problems. In-depth learning is used to semantically segment panoramic images and extract pavement information. Pavement features are used for image registration and removal of dynamic obstacle occlusion can also improve the accuracy of registration. GPS and odometer information are fused for positioning optimization, and multi-frame image overlay is used to fill the gaps to form a map. Finally, the experimental results show that this method improves the accuracy of map while removing dynamic obstacles.
引文
[1] Nugraha B T,Su S F.Towards self-driving car using convolutional neural network and road lane detector[C]// International Conference on Automation,2018.
[2] 杨明.无人自动驾驶车辆研究综述与展望[J].哈尔滨工业大学学报,2006,38(8):1259-1262.Yang Ming.Overview and prospects of the study on driverless vehicles[J].Journal of Harbin Institute of Technology,2006,38(8):1259-1262(in Chinese).
[3] 于明涛.智慧物流体系中的无人配送技术[J].物流技术与应用,2017(11):35.Yu Mingtao.Unmanned distribution technology in intelligent logistics system[J].Logistics & Material Handling,2017(11):35(in Chinese).
[4] Liu C,Xu G,Gao F,et al.Design of disaster relief robot assistant[C]// International Conference on Intelligent Information Technology Application,2013.
[5] H?ne C,Heng L,Lee G H,et al.3D visual perception for self-driving cars using a multi-camera system:calibration,mapping,localization,and obstacle detection[J].Image and Vision Computing,2017,68:14-27.
[6] 余阿东,陈睿炜.汽车自动驾驶技术研究[J].汽车实用技术,2017(2):124-125.Yu Adong,Chen Ruiwei.Research on auto driving technology[J].Automobile Applied Technology,2017(2):124-125(in Chinese).
[7] Lee U,Jung J,Jung S,et al.Development of a self-driving car that can handle the adverse weather[J].International Journal of Automotive Technology,2018,19(1):191-197.
[8] 贺勇,路昊,王春香,等.基于多传感器的车道级高精细地图制作方法[J].长安大学学报(自然科学版),2015(S1):274-278.He Yong,Lu Hao,Wang Chunxiang,et al.Generation of precise lane-level maps based on multi-sensors[J].Journal of Chang’an University(Natural Science Edition),2015(S1):274-278(in Chinese).
[9] Li L,Yang M,Wang B,et al.An overview on sensor map based localization for automated driving[C]// 2017 Joint Urban Remote Sensing Event (JURSE),2017.
[10] Guo L,Yang M,Wang B,et al.Occupancy grid based urban localization using weighted point cloud[C]// 2016 IEEE 19th International Conference on Intelligent Transportation Systems(ITSC),2016.
[11] Chabot F,Chaouch M,Rabarisoa J,et al.Deep manta:A coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:1827-1836.
[12] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[13] Fan Y,Cheng H,Xing B B,et al.Study on a stitching algorithm of the iterative closest point based on dynamic hierarchy[J].Journal of Optical Technology,2015,82(1):28-32.
[14] 沈凯,管雪元,李文胜.扩展卡尔曼滤波在组合导航中的应用[J].传感器与微系统,2017(8):158-160.Shen Kai,Guan Xueyuan,Li Wensheng.Application of extended Kalman filter in integrated navigation[J].Transducer and Microsystem Technologies,2017(8):158-160(in Chinese).
[15] Chen L C,Zhu Y,Papandreou G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV),2018:801-818.
[16] Long J,Shelhamer E ,Darrell T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,39(4):640-651.
[17] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[18] Besl P J.Method for registration of 3-D shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[19] Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.
[2] 杨明.无人自动驾驶车辆研究综述与展望[J].哈尔滨工业大学学报,2006,38(8):1259-1262.Yang Ming.Overview and prospects of the study on driverless vehicles[J].Journal of Harbin Institute of Technology,2006,38(8):1259-1262(in Chinese).
[3] 于明涛.智慧物流体系中的无人配送技术[J].物流技术与应用,2017(11):35.Yu Mingtao.Unmanned distribution technology in intelligent logistics system[J].Logistics & Material Handling,2017(11):35(in Chinese).
[4] Liu C,Xu G,Gao F,et al.Design of disaster relief robot assistant[C]// International Conference on Intelligent Information Technology Application,2013.
[5] H?ne C,Heng L,Lee G H,et al.3D visual perception for self-driving cars using a multi-camera system:calibration,mapping,localization,and obstacle detection[J].Image and Vision Computing,2017,68:14-27.
[6] 余阿东,陈睿炜.汽车自动驾驶技术研究[J].汽车实用技术,2017(2):124-125.Yu Adong,Chen Ruiwei.Research on auto driving technology[J].Automobile Applied Technology,2017(2):124-125(in Chinese).
[7] Lee U,Jung J,Jung S,et al.Development of a self-driving car that can handle the adverse weather[J].International Journal of Automotive Technology,2018,19(1):191-197.
[8] 贺勇,路昊,王春香,等.基于多传感器的车道级高精细地图制作方法[J].长安大学学报(自然科学版),2015(S1):274-278.He Yong,Lu Hao,Wang Chunxiang,et al.Generation of precise lane-level maps based on multi-sensors[J].Journal of Chang’an University(Natural Science Edition),2015(S1):274-278(in Chinese).
[9] Li L,Yang M,Wang B,et al.An overview on sensor map based localization for automated driving[C]// 2017 Joint Urban Remote Sensing Event (JURSE),2017.
[10] Guo L,Yang M,Wang B,et al.Occupancy grid based urban localization using weighted point cloud[C]// 2016 IEEE 19th International Conference on Intelligent Transportation Systems(ITSC),2016.
[11] Chabot F,Chaouch M,Rabarisoa J,et al.Deep manta:A coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:1827-1836.
[12] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[13] Fan Y,Cheng H,Xing B B,et al.Study on a stitching algorithm of the iterative closest point based on dynamic hierarchy[J].Journal of Optical Technology,2015,82(1):28-32.
[14] 沈凯,管雪元,李文胜.扩展卡尔曼滤波在组合导航中的应用[J].传感器与微系统,2017(8):158-160.Shen Kai,Guan Xueyuan,Li Wensheng.Application of extended Kalman filter in integrated navigation[J].Transducer and Microsystem Technologies,2017(8):158-160(in Chinese).
[15] Chen L C,Zhu Y,Papandreou G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV),2018:801-818.
[16] Long J,Shelhamer E ,Darrell T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,39(4):640-651.
[17] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[18] Besl P J.Method for registration of 3-D shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[19] Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.